CN110796210A - Method and device for identifying label information - Google Patents
Method and device for identifying label information Download PDFInfo
- Publication number
- CN110796210A CN110796210A CN201810880159.5A CN201810880159A CN110796210A CN 110796210 A CN110796210 A CN 110796210A CN 201810880159 A CN201810880159 A CN 201810880159A CN 110796210 A CN110796210 A CN 110796210A
- Authority
- CN
- China
- Prior art keywords
- product
- picture
- label picture
- product label
- identifying
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Abstract
The invention discloses a method and a device for identifying label information, which are used for obtaining a product label picture and attribute information of a product, identifying text information included in the product label picture based on a convolutional neural network model to obtain an identification result, and determining that the label picture configured for the product is correct if the identification result of the text information is the same as the attribute information of the product, so that the false detection rate of the label information is reduced, and the working efficiency is improved.
Description
Technical Field
The present invention relates to the field of image recognition processing, and in particular, to a method and an apparatus for recognizing tag information.
Background
Energy efficiency labels are usually provided on energy-consuming products or small packages in daily life, and are information labels representing performance indexes such as energy efficiency levels of the products.
At present, the method for identifying the energy efficiency label mainly depends on manual work, staff on a production line need to manually check whether the label is printed wrongly or not and need to check whether the label is attached to a corresponding product or not, the workload of the manual identification method is large, and the staff can have visual fatigue when working for a long time, so that the false inspection rate is easily improved.
Disclosure of Invention
The invention aims to provide a method and a device for identifying tag information, which are used for reducing the false detection rate of the tag information and improving the working efficiency.
The purpose of the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a method for identifying tag information, including:
acquiring a product label picture and attribute information of the product;
identifying the text information included in the product label picture based on a convolutional neural network model to obtain a first identification result; the text information is used for representing the attribute of the product corresponding to the product label picture;
and if the first identification result is determined to be the same as the acquired attribute information of the product, determining that the product label picture configured for the product is correct.
Optionally, the identifying the text information included in the product tag picture based on the convolutional neural network model includes:
classifying the text information included in the product label picture based on a convolutional neural network model to obtain characters of different classes;
and recognizing the classified characters of different classes by using an Optical Character Recognition (OCR) algorithm.
Optionally, after the energy efficiency tag picture is acquired and before the text information included in the product tag picture is identified based on the convolutional neural network model, the method further includes:
processing the product label picture by at least one of the following steps: image binarization, image denoising, contrast adjustment and rotation correction.
Optionally, the product label picture further includes a two-dimensional code and/or a bar code;
the acquiring of the attribute information of the product comprises:
identifying a two-dimensional code and/or a bar code included in the product label picture to acquire attribute information of the product;
in a second aspect, the present invention provides an apparatus for identifying tag information, including:
the acquisition unit is used for acquiring a product label picture and attribute information of the product;
the processing unit is used for identifying the text information included in the product label picture acquired by the acquisition unit based on a convolutional neural network model to obtain a first identification result;
the text information is used for representing the attribute of the product corresponding to the product label picture;
a determining unit, configured to determine that the product label picture configured for the product is correct when it is determined that the first identification result is the same as the acquired attribute information of the product.
Optionally, the processing unit is specifically configured to identify text information included in the product tag picture based on a convolutional neural network model as follows:
classifying the text information included in the product label picture based on a convolutional neural network model to obtain characters of different classes;
and recognizing the classified characters of different classes by using an Optical Character Recognition (OCR) algorithm.
Optionally, the processing unit is further configured to: processing the product label picture by at least one of the following steps: image binarization, image denoising, contrast adjustment and rotation correction.
Optionally, the product label picture further includes a two-dimensional code and/or a barcode.
Optionally, the obtaining unit obtains the attribute information of the product specifically as follows:
and identifying the two-dimensional code and/or the bar code included in the product label picture, and acquiring the attribute information of the product.
In a third aspect, the present invention provides an apparatus for identifying tag information, including:
a memory for storing program instructions;
a processor for calling the program instructions stored in the memory and executing the method of the first aspect according to the obtained program.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions which, when run on a computer, cause the computer to perform the method of the first aspect.
Drawings
Fig. 1 is a method for identifying tag information according to an embodiment of the present disclosure;
fig. 2 is a block diagram of an apparatus for identifying tag information according to an embodiment of the present disclosure;
fig. 3 is a schematic view of another identification apparatus for tag information according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 shows a method for identifying tag information according to an embodiment of the present application, where an execution subject of the method shown in fig. 1 may be an apparatus for identifying tag information, and referring to fig. 1, the method includes:
s101: and acquiring a label picture of the product and attribute information of the product.
In the embodiment of the application, the label picture of the product may include text information, and the text information is used for representing the attribute of the product.
It is understood that in the embodiments of the present application, the image acquisition may be performed by an image acquisition device, for example, a camera, a video camera, or the like.
S102: and identifying the text information in the product label picture based on the convolutional neural network model.
In the embodiment of the application, the text information included in the product label can be identified by utilizing the pre-trained convolutional neural network model.
Specifically, in one possible implementation, the text information included in the product label picture may be classified based on a convolutional neural network model to distinguish different characters, and the different characters may be recognized by using an Optical Character Recognition (OCR) technique.
Because the convolutional neural network model processes a single character, before classifying the text information, the text information in the product label picture needs to be extracted, and the extracted text information is segmented to obtain one character.
S103: and if the identification result of the text information is the same as the acquired attribute information of the product, determining that the product label picture configured for the product is correct.
In the embodiment of the application, the text information in the product label picture is identified to obtain an identification result, the text information in the product label picture is compared with the obtained product attribute information, and when the identification result of the text information in the product label picture is determined to be consistent with the obtained product attribute information, the product label picture configured for the product is determined to be correct.
Further, before text information included in the product label picture is identified based on the convolutional neural network model, after the energy efficiency label picture is collected, the collected energy efficiency label picture can be preprocessed to obtain a high-resolution picture.
Specifically, at least one of the following preprocessing processes may be performed on the picture: image binarization, image denoising, contrast adjustment and rotation correction.
In practical applications, the picture of the energy efficiency label is usually printed in a paper form and attached to a corresponding product, but the paper form is only one expression form, and the embodiment of the application is not limited thereto. For example, the Document may be in the form of Portable Document Format (PDF).
In general, a PDF file may have multiple pages of contents, and a single page PDF file needs to be converted into a picture. After the single page content extracted from the PDF is converted into a picture, the picture may need to be preprocessed due to noise, unclear text, confusion and complexity, and the like of the picture.
For a multi-page PDF file, PDF is firstly split into a plurality of single pages by PDF processing software, and the single-page PDF file is converted into a high-resolution picture by ImageMagick software.
Further, the product label picture can also comprise a two-dimensional code and/or a bar code.
Specifically, because most of texts in the energy efficiency label picture are rendering fonts or artistic fonts, and the bar codes, the two-dimensional codes and the like in the energy efficiency label picture have the phenomena of distortion, incompleteness and the like, the identification difficulty is high, and the energy efficiency label picture can be preprocessed.
For example, the specific processing operations include: the image can be subjected to binarization, denoising, contrast adjustment, rotation correction and other processing, so that the image quality is improved, and the interference is reduced.
It is to be understood that the preprocessing manner in the embodiment of the present application is not limited thereto, and for example, median filtering, edge detection, and the like may be performed on the image.
In a possible implementation manner, the convolutional neural network model in the embodiment of the present application may be obtained by training in the following manner:
inputting the character picture set into a convolutional neural network, artificially classifying characters in the input character picture, training parameters in the model by using a deep learning algorithm, and continuously correcting the model to finally obtain an optimal classification model.
The trained optimal weight values, bias values and other parameter values of the neurons capable of realizing classification are stored in the model.
It can be understood that the classification model is a convolutional neural network model, and through the training and learning process, the trained convolutional neural network model has the capability of classifying and recognizing characters.
Specifically, when the convolutional neural network model is used for identifying text information in a product label picture, convolutional kernel convolution processing of a neural network algorithm can be used for forming a multidimensional vector representing picture characteristics. Different pictures correspond to different vectors, and different characters are distinguished according to the difference of the vectors, for example, in a neural network, whether the characters can belong to one type can be judged according to the included angle between the vectors.
For example, if a word has a plurality of different fonts or colors, etc., words of the same word with different characteristics may be classified into one category. When the text information in the tag information is input into the convolutional neural network model, a plurality of different types of forms may be stored in the convolutional neural network model for the same word, and then the convolutional neural network model can identify the word in the tag information according to the probability of the word with each characteristic.
It should be noted that different types of words may include different fonts, different colors, etc. of the same word.
It can be understood that, when convolution kernel convolution processing is used, text information can be identified according to a mode that one convolution kernel convolution processes the color of a character, the other convolution kernel convolution processes the line of the character, and the like, so as to obtain a multidimensional vector.
Furthermore, the two-dimensional code and/or the bar code included in the product label picture can be identified, and the attribute information of the product can be acquired.
It is understood that the two-dimensional code and/or the bar code may be scanned by the terminal to identify information corresponding to the two-dimensional code or the bar code.
When the text information in the product label is identified, the corresponding information of the product can be obtained, for example, the identification result of the text information can be regarded as "information 1", and when the two-dimensional code or the bar code in the product label is identified, the attribute information of the product can be obtained, for example, the identification result of the two-dimensional code and/or the bar code can be regarded as "information 2".
In a possible implementation mode, the information 1 and the information 2 can be compared to judge whether the two are consistent, if so, the product label can be determined to correspond to the product, and if not, the product label can be determined to not correspond to the product.
It can be understood that if it is determined that the recognition result of the two-dimensional code or the barcode is the same as the recognition result of the text information included in the image for recognizing the product tag, it is determined that the image for the product tag configured for the product is correct.
Based on the same concept as the above embodiment of the identification method for tag information, an embodiment of the present invention further provides an identification apparatus for tag information, which is shown in fig. 2. The device includes: an acquisition unit 101, a processing unit 102, and a determination unit 103.
The obtaining unit 101 is configured to obtain a product label picture and attribute information of a product.
The processing unit 102 is configured to identify, based on the convolutional neural network model, text information included in the product tag picture acquired by the acquisition unit 101, and obtain a first identification result.
The text information is used for representing the attribute of the product corresponding to the product label picture.
A determining unit 103, configured to determine that the product label picture configured for the product is correct when it is determined that the first identification result is the same as the acquired attribute information of the product.
Specifically, the processing unit 102 is specifically configured to identify text information included in the product tag picture based on the convolutional neural network model as follows:
classifying text information included in the product label picture based on a convolutional neural network model to obtain characters of different classes;
and recognizing the classified characters of different classes by using an Optical Character Recognition (OCR) algorithm.
Further, the processing unit 102 is further configured to: processing the product label picture by at least one of the following steps: image binarization, image denoising, contrast adjustment and rotation correction.
Optionally, the product label picture further includes a two-dimensional code and/or a bar code.
Further, the obtaining unit 101 is specifically configured to obtain the attribute information of the product as follows: and identifying the two-dimensional code and/or the bar code included in the product label picture, and acquiring the attribute information of the product.
It should be noted that, for the implementation of the functions of each unit in the above-mentioned tag information identification apparatus in the embodiment of the present invention, reference may be further made to the description of the related method embodiment, which is not described herein again.
It is to be understood that the terms "first," "second," and the like in the description herein are used for descriptive purposes only and not for purposes of indicating or implying relative importance, nor order.
Specifically, in practical applications, the following program modules may be installed in the tag information identification apparatus based on a computer programming language python: zbar module, pyzbar module, pytesseract module.
Zbar and pyzbar are scanning tools of bar codes/two-dimensional codes, a zbar module is used for identifying bar code information, a pyzbar module is used for identifying two-dimensional code information, and a pytesseract module can call Tesseract-OCR to identify characters and store text information in a text file.
The Tesseract-OCR module is an open-source OCR engine compiled and installed under a centros 7 system, compiling can be carried out on the basis of an OCR engine Tesseract 4.0 of a Long Short-Term Memory network (LSTM), and an LSTM neural network training model is adopted on the basis of a deep learning algorithm to be called by the Tesseract-OCR engine.
An embodiment of the present application further provides another apparatus for identifying tag information, as shown in fig. 3, the apparatus includes:
a memory 202 for storing program instructions.
A transceiver 201 for receiving and transmitting instructions identifying tag information.
And the processor 200 is configured to call the program instructions stored in the memory, and execute any method flow described in the embodiments of the present application according to the obtained program according to the instructions received by the transceiver 201. The processor 200 is used to implement the methods performed by the processing unit (102) and the determining unit (103) shown in fig. 2.
Where in fig. 3 the bus architecture may include any number of interconnected buses and bridges, with various circuits of one or more processors, represented by processor 200, and memory, represented by memory 202, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface.
The transceiver 201 may be a number of elements, including a transmitter and a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 200 is responsible for managing the bus architecture and general processing, and the memory 202 may store data used by the processor 200 in performing operations.
The processor 200 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or a Complex Programmable Logic Device (CPLD).
Embodiments of the present application also provide a computer storage medium for storing computer program instructions for any apparatus described in the embodiments of the present application, which includes a program for executing any method provided in the embodiments of the present application.
The computer storage media may be any available media or data storage device that can be accessed by a computer, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs)), etc.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for identifying tag information, comprising:
acquiring a product label picture and acquiring attribute information of the product;
identifying text information included in the product label picture based on a convolutional neural network model to obtain a first identification result;
the text information is used for representing the attribute of the product corresponding to the product label picture;
and if the first identification result is determined to be the same as the acquired attribute information of the product, determining that the product label picture configured for the product is correct.
2. The method of claim 1, wherein the identifying textual information included in the product tag picture based on the convolutional neural network model comprises:
classifying the text information included in the product label picture according to characters based on a convolutional neural network model to obtain characters of different classes;
and recognizing the classified characters of different classes by using an Optical Character Recognition (OCR) algorithm.
3. The method of claim 1 or 2, wherein after acquiring the energy efficiency tag picture and before identifying textual information contained in the product tag picture based on a convolutional neural network model, the method further comprises:
processing the product label picture by at least one of the following steps: image binarization, image denoising, contrast adjustment and rotation correction.
4. The method of claim 1, wherein the product label picture further comprises a two-dimensional code and/or a bar code;
the acquiring of the attribute information of the product comprises:
and identifying the two-dimensional code and/or the bar code included in the product label picture, and acquiring the attribute information of the product.
5. An apparatus for identifying tag information, comprising:
the acquisition unit is used for acquiring a product label picture and attribute information of the product;
the processing unit is used for identifying the text information included in the product label picture acquired by the acquisition unit based on a convolutional neural network model to obtain a first identification result;
the text information is used for representing the attribute of the product corresponding to the product label picture;
a determining unit, configured to determine that the product label picture configured for the product is correct when it is determined that the first identification result is the same as the acquired attribute information of the product.
6. The apparatus of claim 5, wherein the processing unit is specifically configured to identify textual information included in the product tag picture based on a convolutional neural network model as follows:
classifying the text information included in the product label picture based on a convolutional neural network model to obtain characters of different classes;
and recognizing the classified characters of different classes by using an Optical Character Recognition (OCR) algorithm.
7. The apparatus of claim 5 or 6, wherein the processing unit is further to: processing the product label picture by at least one of the following steps: image binarization, image denoising, contrast adjustment and rotation correction.
8. The apparatus of claim 5, wherein the product label picture further comprises a two-dimensional code and/or a bar code;
the obtaining unit obtains the attribute information of the product specifically as follows:
and identifying the two-dimensional code and/or the bar code included in the product label picture, and acquiring the attribute information of the product.
9. An apparatus for processing application data, comprising:
a memory for storing program instructions;
a processor for calling the program instructions stored in the memory and executing the method of any one of claims 1 to 4 according to the obtained program.
10. A computer readable storage medium having stored thereon computer instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810880159.5A CN110796210A (en) | 2018-08-03 | 2018-08-03 | Method and device for identifying label information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810880159.5A CN110796210A (en) | 2018-08-03 | 2018-08-03 | Method and device for identifying label information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110796210A true CN110796210A (en) | 2020-02-14 |
Family
ID=69425768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810880159.5A Pending CN110796210A (en) | 2018-08-03 | 2018-08-03 | Method and device for identifying label information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796210A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112164057A (en) * | 2020-10-09 | 2021-01-01 | 珠海格力电器股份有限公司 | Qualified label detection method, storage medium and electronic equipment |
| CN113419659A (en) * | 2021-08-23 | 2021-09-21 | 深圳市信润富联数字科技有限公司 | Method, system, program product and storage medium for constructing label template |
| CN113962231A (en) * | 2021-10-13 | 2022-01-21 | 杭州胜铭纸业有限公司 | Optical identification comparison method and system for information codes of packing cases |
| CN116563841A (en) * | 2023-07-07 | 2023-08-08 | 广东电网有限责任公司云浮供电局 | Detection method and detection device for power distribution network equipment identification plate and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022805A (en) * | 2016-05-25 | 2016-10-12 | 华中科技大学 | Anti-fake traceablility system and method based on label reading |
| CN106446896A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Character segmentation method and device and electronic equipment |
| CN106446954A (en) * | 2016-09-29 | 2017-02-22 | 南京维睛视空信息科技有限公司 | Character recognition method based on depth learning |
-
2018
- 2018-08-03 CN CN201810880159.5A patent/CN110796210A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446896A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Character segmentation method and device and electronic equipment |
| CN106022805A (en) * | 2016-05-25 | 2016-10-12 | 华中科技大学 | Anti-fake traceablility system and method based on label reading |
| CN106446954A (en) * | 2016-09-29 | 2017-02-22 | 南京维睛视空信息科技有限公司 | Character recognition method based on depth learning |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112164057A (en) * | 2020-10-09 | 2021-01-01 | 珠海格力电器股份有限公司 | Qualified label detection method, storage medium and electronic equipment |
| CN113419659A (en) * | 2021-08-23 | 2021-09-21 | 深圳市信润富联数字科技有限公司 | Method, system, program product and storage medium for constructing label template |
| CN113962231A (en) * | 2021-10-13 | 2022-01-21 | 杭州胜铭纸业有限公司 | Optical identification comparison method and system for information codes of packing cases |
| CN113962231B (en) * | 2021-10-13 | 2024-03-26 | 杭州胜铭纸业有限公司 | Packaging box information code optical identification comparison method and system |
| CN116563841A (en) * | 2023-07-07 | 2023-08-08 | 广东电网有限责任公司云浮供电局 | Detection method and detection device for power distribution network equipment identification plate and electronic equipment |
| CN116563841B (en) * | 2023-07-07 | 2023-11-10 | 广东电网有限责任公司云浮供电局 | Detection method and detection device for power distribution network equipment identification plate and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902622B (en) | Character detection and identification method for boarding check information verification | |
| US8923608B2 (en) | Pre-screening training data for classifiers | |
| CN110942074B (en) | Character segmentation recognition method and device, electronic equipment and storage medium | |
| CN110796210A (en) | Method and device for identifying label information | |
| CN110598686B (en) | Invoice identification method, system, electronic equipment and medium | |
| CN109934255B (en) | Model fusion method suitable for classification and identification of delivered objects of beverage bottle recycling machine | |
| CN105574513A (en) | Character detection method and device | |
| JP2008159056A (en) | Classification through generative model of feature occurring in image | |
| US20200134382A1 (en) | Neural network training utilizing specialized loss functions | |
| CN108734159B (en) | Method and system for detecting sensitive information in image | |
| CN113963147B (en) | Key information extraction method and system based on semantic segmentation | |
| CN113158895B (en) | Bill identification method and device, electronic equipment and storage medium | |
| US11600088B2 (en) | Utilizing machine learning and image filtering techniques to detect and analyze handwritten text | |
| CN110705225A (en) | Contract marking method and device | |
| CN113128536A (en) | Unsupervised learning method, system, computer device and readable storage medium | |
| CN110309301B (en) | Enterprise category classification method and device and intelligent terminal | |
| US11023720B1 (en) | Document parsing using multistage machine learning | |
| CN113673528B (en) | Text processing method, text processing device, electronic equipment and readable storage medium | |
| CN112508000B (en) | Method and equipment for generating OCR image recognition model training data | |
| CN112613367A (en) | Bill information text box acquisition method, system, equipment and storage medium | |
| CN117095402A (en) | Method and device for processing signing and receiving orders, medium and electronic equipment | |
| CN116311276A (en) | Document image correction method, device, electronic equipment and readable medium | |
| US11715288B2 (en) | Optical character recognition using specialized confidence functions | |
| CN114612919A (en) | Bill information processing system, method and device | |
| CN114519416A (en) | Model distillation method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |
|
| RJ01 | Rejection of invention patent application after publication |